@inproceedings{zhang-etal-2024-gla,
title = "Gla-{AI}4{B}io{M}ed at {RRG}24: Visual Instruction-tuned Adaptation for Radiology Report Generation",
author = "Zhang, Xi and
Meng, Zaiqiao and
Lever, Jake and
Ho, Edmond S.L.",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Miwa, Makoto and
Roberts, Kirk and
Tsujii, Junichi",
booktitle = "Proceedings of the 23rd Workshop on Biomedical Natural Language Processing",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.bionlp-1.54",
doi = "10.18653/v1/2024.bionlp-1.54",
pages = "624--634",
abstract = "This paper introduces a radiology-focused visual language model designed to generate radiology reports from chest X-rays. Building on previous findings that large language models can acquire multimodal capabilities when aligned with pretrained vision encoders, we demonstrate similar potential with chest X-ray images. The model combines an image encoder (CLIP) with a fine-tuned large language model (LLM) based on the Vicuna-7B architecture. The training process involves a two-stage approach: initial alignment of chest X-ray features with the LLM, followed by fine-tuning for radiology report generation. The study highlights the importance of generating both FINDINGS and IMPRESSIONS sections in radiology reports and evaluates the model{'}s performance using various metrics, achieving notable accuracy in generating high-quality medical reports. The research also addresses the need for domain-specific fine-tuning to capture the intricate details necessary for accurate medical interpretations and reports.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-gla">
<titleInfo>
<title>Gla-AI4BioMed at RRG24: Visual Instruction-tuned Adaptation for Radiology Report Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaiqiao</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jake</namePart>
<namePart type="family">Lever</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edmond</namePart>
<namePart type="given">S.L.</namePart>
<namePart type="family">Ho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Workshop on Biomedical Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Miwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces a radiology-focused visual language model designed to generate radiology reports from chest X-rays. Building on previous findings that large language models can acquire multimodal capabilities when aligned with pretrained vision encoders, we demonstrate similar potential with chest X-ray images. The model combines an image encoder (CLIP) with a fine-tuned large language model (LLM) based on the Vicuna-7B architecture. The training process involves a two-stage approach: initial alignment of chest X-ray features with the LLM, followed by fine-tuning for radiology report generation. The study highlights the importance of generating both FINDINGS and IMPRESSIONS sections in radiology reports and evaluates the model’s performance using various metrics, achieving notable accuracy in generating high-quality medical reports. The research also addresses the need for domain-specific fine-tuning to capture the intricate details necessary for accurate medical interpretations and reports.</abstract>
<identifier type="citekey">zhang-etal-2024-gla</identifier>
<identifier type="doi">10.18653/v1/2024.bionlp-1.54</identifier>
<location>
<url>https://aclanthology.org/2024.bionlp-1.54</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>624</start>
<end>634</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Gla-AI4BioMed at RRG24: Visual Instruction-tuned Adaptation for Radiology Report Generation
%A Zhang, Xi
%A Meng, Zaiqiao
%A Lever, Jake
%A Ho, Edmond S.L.
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Miwa, Makoto
%Y Roberts, Kirk
%Y Tsujii, Junichi
%S Proceedings of the 23rd Workshop on Biomedical Natural Language Processing
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F zhang-etal-2024-gla
%X This paper introduces a radiology-focused visual language model designed to generate radiology reports from chest X-rays. Building on previous findings that large language models can acquire multimodal capabilities when aligned with pretrained vision encoders, we demonstrate similar potential with chest X-ray images. The model combines an image encoder (CLIP) with a fine-tuned large language model (LLM) based on the Vicuna-7B architecture. The training process involves a two-stage approach: initial alignment of chest X-ray features with the LLM, followed by fine-tuning for radiology report generation. The study highlights the importance of generating both FINDINGS and IMPRESSIONS sections in radiology reports and evaluates the model’s performance using various metrics, achieving notable accuracy in generating high-quality medical reports. The research also addresses the need for domain-specific fine-tuning to capture the intricate details necessary for accurate medical interpretations and reports.
%R 10.18653/v1/2024.bionlp-1.54
%U https://aclanthology.org/2024.bionlp-1.54
%U https://doi.org/10.18653/v1/2024.bionlp-1.54
%P 624-634
Markdown (Informal)
[Gla-AI4BioMed at RRG24: Visual Instruction-tuned Adaptation for Radiology Report Generation](https://aclanthology.org/2024.bionlp-1.54) (Zhang et al., BioNLP-WS 2024)
ACL